Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/danielrosehill/claude-image-production-plugin/vectorizenpx skills add danielrosehill/Claude-Image-Production-Plugin --skill vectorizegit clone --depth 1 https://github.com/danielrosehill/Claude-Image-Production-PluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/danielrosehill/claude-image-production-plugin/vectorize)<a href="https://agentmods.dev/skills/danielrosehill/claude-image-production-plugin/vectorize"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-image-production-plugin/vectorize.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00069 | $0.01155 |
| Opus 5 | $0.00034 | $0.00577 |
| Sonnet 5 | $0.00014 | $0.00231 |
| Haiku 4.5 | $0.00007 | $0.00115 |
Grade A, and why
vectorize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vectorize
Convert raster images to SVG via vtracer. vtracer is a colour-clustering tracer — much better than potrace for full-colour images, comparable for B/W line art. Installed as a Python wheel in the plugin venv (bundled Rust binary, no cargo needed at install time).
When to use
- Recover an editable vector logo from a raster (PNG/JPEG).
- Convert a flat illustration / icon / diagram into SVG for crisp scaling.
- Stylize a photo into a flat-colour vector (large
--filter-speckle+ low--color-precision). - Pre-step before
svg-to-rasterif you want to upscale a small raster losslessly.
Do not use this skill when:
- Source is a complex photograph and you want photo-realism — vector tracing always loses gradients/texture; use
upscale-imagefor raster upscaling instead. - You need OCR'd text inside the SVG — vtracer traces strokes, not text. Use a separate OCR step.
- Input is already SVG — no-op.
Inputs
- Input — image file or directory. Required.
- Output dir — default:
<input-dir>/svg/. Never overwrites originals. - Mode —
color(default, multi-colour with clustering) orbinary(B/W line art, faster, smaller output). - Color precision —
1..8, default6. Lower = fewer colours = smaller / more abstract SVG. - Layer difference —
0..255, default16. Larger = fewer layers, simpler output. - Filter speckle — pixels, default
4. Discards regions smaller than N pixels — raise to denoise. - Path simplification —
corner threshold(default60deg),length threshold(default4.0),splice threshold(default45deg). Most users won't tune these; expose only if asked. - Recursive —
--recursivefor directory descent.
Procedure
-
Resolve venv:
VENV_DIR="${CLAUDE_USER_DATA:-${XDG_DATA_HOME:-$HOME/.local/share}/claude-plugins}/image-production/venv". -
Verify
vtraceris importable:"$VENV_DIR/bin/python" -c "import vtracer" 2>&1
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 87 lines · 69 tokens per session scan A 6621ddd3871b
vectorize is a skill published in the GitHub repository danielrosehill/Claude-Image-Production-Plugin (16 stars, last pushed 17d ago), licensed MIT. It adds 69 tokens to every session and 1,155 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
hallmark
Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
prototype-web
可点击的功能性 Web 原型, 含导航、英雄区、特性区、CTA.
desktop-principles
Desktop-specific UX principles - hover states, pointer precision, keyboard shortcuts, multi-window, focus management. Covers macOS, Windows, Linux, web desktop.
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约，产出 UI-DESIGN.md。四端通用。.
drawio-diagram
Generate draw.io network diagrams — native .drawio files with CLI export (PNG/SVG/PDF), plus browser-based Mermaid/XML/CSV via MCP server. Use when creating network topology diagrams, generating architecture visuals, exporting diagrams to PNG or PDF, or building draw.io files from discovery data.